{"total":255,"rows":[{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712,"area":null},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243,"area":null},{"id":"2303.09522","title":"P+: Extended Textual Conditioning in Text-to-Image Generation","created":"2023-03-16","cited_by_count":242,"area":null},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196,"area":null},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147,"area":null},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126,"area":null},{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2308.01862","title":"Wider and Deeper LLM Networks are Fairer LLM Evaluators","created":"2023-08-03","cited_by_count":94,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2112.09130","title":"Ensembling Off-the-shelf Models for GAN Training","created":"2021-12-16","cited_by_count":86,"area":null},{"id":"2112.00719","title":"HyperInverter: Improving StyleGAN Inversion via Hypernetwork","created":"2021-12-01","cited_by_count":85,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66,"area":null},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65,"area":null},{"id":"2404.14394","title":"A Multimodal Automated Interpretability Agent","created":"2024-04-22","cited_by_count":63,"area":"agents"},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62,"area":null},{"id":"2201.13433","title":"Third Time's the Charm? Image and Video Editing with StyleGAN3","created":"2022-01-31","cited_by_count":54,"area":null},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54,"area":"diffusion"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2311.17137","title":"Generative Models: What Do They Know? Do They Know Things? Let's Find Out!","created":"2023-11-28","cited_by_count":50,"area":"diffusion"},{"id":"2308.01544","title":"Multimodal Neurons in Pretrained Text-Only Transformers","created":"2023-08-03","cited_by_count":49,"area":null},{"id":"2404.00859","title":"Do language models plan ahead for future tokens?","created":"2024-04-01","cited_by_count":49,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2307.14008","title":"Adaptive Frequency Filters As Efficient Global Token Mixers","created":"2023-07-26","cited_by_count":45,"area":null},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2210.15127","title":"Rethinking the Reverse-engineering of Trojan Triggers","created":"2022-10-27","cited_by_count":39,"area":"safety"},{"id":"2402.15390","title":"Explorations of Self-Repair in Language Models","created":"2024-02-23","cited_by_count":39,"area":null},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2303.13995","title":"LINe: Out-of-Distribution Detection by Leveraging Important Neurons","created":"2023-03-24","cited_by_count":34,"area":null},{"id":"2302.10908","title":"Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment","created":"2023-02-13","cited_by_count":33,"area":null},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2204.06504","title":"DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualization","created":"2022-04-13","cited_by_count":32,"area":null},{"id":"2309.03886","title":"FIND: A Function Description Benchmark for Evaluating Interpretability Methods","created":"2023-09-07","cited_by_count":32,"area":null},{"id":"2402.18496","title":"Language Models Represent Beliefs of Self and Others","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2406.02128","title":"Iteration Head: A Mechanistic Study of Chain-of-Thought","created":"2024-06-04","cited_by_count":31,"area":"lr"},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2304.09707","title":"Disentangling Neuron Representations with Concept Vectors","created":"2023-04-19","cited_by_count":28,"area":"mechinterp"},{"id":"2306.02879","title":"Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization","created":"2023-06-05","cited_by_count":28,"area":null},{"id":"2202.03482","title":"Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence","created":"2022-02-07","cited_by_count":25,"area":null},{"id":"2206.15465","title":"Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values","created":"2022-06-30","cited_by_count":25,"area":null},{"id":"2312.03656","title":"Interpretability Illusions in the Generalization of Simplified Models","created":"2023-12-06","cited_by_count":25,"area":null},{"id":"2407.01067","title":"Human-like object concept representations emerge naturally in multimodal large language models","created":"2024-07-01","cited_by_count":25,"area":"mllm"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2405.16534","title":"Pruning for Robust Concept Erasing in Diffusion Models","created":"2024-05-26","cited_by_count":22,"area":"diffusion"},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22,"area":null},{"id":"2306.02585","title":"MotionTrack: Learning Motion Predictor for Multiple Object Tracking","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2103.00229","title":"Neuron Coverage-Guided Domain Generalization","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2405.06855","title":"Linear Explanations for Individual Neurons","created":"2024-05-10","cited_by_count":19,"area":null},{"id":"2101.03049","title":"InMoDeGAN: Interpretable Motion Decomposition Generative Adversarial Network for Video Generation","created":"2021-01-08","cited_by_count":18,"area":null},{"id":"2112.03245","title":"GAM Changer: Editing Generalized Additive Models with Interactive Visualization","created":"2021-12-06","cited_by_count":18,"area":null},{"id":"2305.18512","title":"A Rainbow in Deep Network Black Boxes","created":"2023-05-29","cited_by_count":18,"area":null},{"id":"2307.05471","title":"Scale Alone Does not Improve Mechanistic Interpretability in Vision Models","created":"2023-07-11","cited_by_count":18,"area":"mechinterp"},{"id":"2203.14196","title":"HINT: Hierarchical Neuron Concept Explainer","created":"2022-03-27","cited_by_count":17,"area":null},{"id":"2211.11426","title":"Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations","created":"2022-11-21","cited_by_count":17,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2208.00781","title":"Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods","created":"2022-07-26","cited_by_count":15,"area":null},{"id":"2310.18443","title":"Towards a fuller understanding of neurons with Clustered Compositional Explanations","created":"2023-10-27","cited_by_count":15,"area":null},{"id":"2503.23135","title":"LSNet: See Large, Focus Small","created":"2025-03-29","cited_by_count":15,"area":null},{"id":"2511.22697","title":"Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations","created":"2025-11-27","cited_by_count":15,"area":"mllm"},{"id":"2106.01505","title":"Barbershop: GAN-based Image Compositing using Segmentation Masks","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2104.04785","title":"Generating Physically-Consistent Satellite Imagery for Climate Visualizations","created":"2021-04-10","cited_by_count":13,"area":null},{"id":"2404.14349","title":"Automatic Discovery of Visual Circuits","created":"2024-04-22","cited_by_count":13,"area":null},{"id":"2104.00358","title":"Nine Potential Pitfalls when Designing Human-AI Co-Creative Systems","created":"2021-04-01","cited_by_count":12,"area":null},{"id":"2108.12931","title":"NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks","created":"2021-08-29","cited_by_count":12,"area":null},{"id":"2210.09404","title":"Measures of Information Reflect Memorization Patterns","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2305.02469","title":"The System Model and the User Model: Exploring AI Dashboard Design","created":"2023-05-04","cited_by_count":12,"area":null},{"id":"2309.07398","title":"Semantic Adversarial Attacks via Diffusion Models","created":"2023-09-14","cited_by_count":12,"area":"diffusion"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2109.04374","title":"IFBiD: Inference-Free Bias Detection","created":"2021-09-09","cited_by_count":11,"area":null},{"id":"2405.16714","title":"Crafting Interpretable Embeddings by Asking LLMs Questions","created":"2024-05-26","cited_by_count":11,"area":null},{"id":"2403.13771","title":"Interpreting Neurons in Deep Vision Networks with Language Models","created":"2024-03-20","cited_by_count":10,"area":null},{"id":"2102.08540","title":"Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs","created":"2021-02-17","cited_by_count":9,"area":null},{"id":"2105.02939","title":"PCE-PINNs: Physics-Informed Neural Networks for Uncertainty Propagation in Ocean Modeling","created":"2021-05-05","cited_by_count":9,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2410.12327","title":"Neuron-based Personality Trait Induction in Large Language Models","created":"2024-10-16","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2503.21730","title":"Effective Skill Unlearning through Intervention and Abstention","created":"2025-03-27","cited_by_count":9,"area":"safety"},{"id":"2102.09235","title":"Deep Residual Networks Learn the Geodesic Curve in the Wasserstein Space","created":"2021-02-18","cited_by_count":8,"area":null},{"id":"2201.06515","title":"Differentiable Rule Induction with Learned Relational Features","created":"2022-01-17","cited_by_count":8,"area":null},{"id":"2212.09735","title":"Correspondence Distillation from NeRF-based GAN","created":"2022-12-19","cited_by_count":8,"area":null},{"id":"2305.01939","title":"Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models","created":"2023-05-03","cited_by_count":8,"area":null},{"id":"2310.05331","title":"Unlearning with Fisher Masking","created":"2023-10-09","cited_by_count":8,"area":"safety"},{"id":"2409.15827","title":"Unveiling Language Competence Neurons: A Psycholinguistic Approach to Model Interpretability","created":"2024-09-24","cited_by_count":8,"area":null},{"id":"2505.16538","title":"Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null}],"next_cursor":"100"}